M6 Mac mini vs RTX 5090

Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.

M6 Mac mini2 sourced runs · best 52.5 tok/s

RTX 509023 verified runs · best 446.7 tok/s

Specs and evidence

	M6 Mac mini	RTX 5090
VRAM	—	32 GB
Sourced runs on the board	2	23
Models measured	1	16
Best output tok/s	52.5 tok/s	446.7 tok/s
Highest measured peak VRAM	—	31.3 GB
Street price (latest snapshot)	—	—

Sourced rows only. Peak VRAM is recorded by the person who ran the benchmark, so it is a floor for what the card can hold, not a specification. Price snapshots.

The measured matrix

Model	M6 Mac mini	RTX 5090
NVIDIA-Nemotron-3.5-Lightning-30B-A3B	—	446.7 NVFP4
Qwen3.8-27B	—	435.1 IQ4_XS
Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP	—	283.1 NVFP4
Kimi-Linear-48B-A3B-Instruct	—	280.8 IQ4_XS
Ornith-1.5-35B-A3B	—	258.8 NVFP4
North-Mini-Code-1.0	—	258.4 UD-Q6_K_XL
Qwen3.6-35B-A3B-MTP	—	222.9 Unsloth-Dynamic-IQ4_XS
Laguna-XS-2.1	—	216.7 NVFP4
KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM	—	201.2 W4A16
Ornith-1.0-35B	—	196.6 AWQ
Muse-Glimmer-30B	—	124.8 NVFP4
Qwen3.6-27B	—	120.9 NVFP4
Huihui-Qwen3.8-27B-abliterated	—	117.7 NVFP4
Qwen3.8-27B-5090-goldilocks	—	93.5 Q6_K
Ternary Bonsai 2 27B	52.5 2-bit ternary LUT	—
Qwen3.6-27B-MTP	—	28.3 Q5_K_M
DeepSeek-V4-Flash-0731	—	26.4 MXFP4

17 rows · 1 models on M6 Mac mini, 16 on RTX 5090 — no verified overlap yet, each side shows its own bests · data as of Oct 17, 2026. Full rules: methodology.

Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board